amine-akrout/llm-based-recommender

AI-powered fashion recommendation system leveraging LLMs, embeddings, and retrieval techniques to deliver personalized shopping experiences.

34
/ 100
Emerging

Implements a RAG pipeline combining FAISS vector search, BM25 lexical matching, and cross-encoder reranking to handle both semantic and keyword-based queries across a 30K-product dataset. The system uses LangGraph for orchestration, integrating FastAPI for scalable API serving and Streamlit for an interactive chatbot UI, with support for both local Ollama models and GPT-4o-mini through configurable LLM backends.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

30

Forks

8

Language

Python

License

Last pushed

Jul 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/amine-akrout/llm-based-recommender"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.